{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39655267", "kind": "science-record", "revision": 3, "content_hash": "sha256:dfef7c5ade3a0edfb38d2107c7a1b13b098f61692e543d9f52afb84ee238cb3e", "created_at": "2026-11-01T20:29:57Z", "updated_at": "2026-11-01T22:55:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of gastric cancer biomarkers through in-silico analysis of microarray based datasets.", "doi": "10.1016/j.bbrep.2024.101880", "pmid": "39655267", "authors": ["Arbaz Akhtar", "Yasir Hameed", "Samina Ejaz", "Iqra Abdullah"], "journal": "Biochemistry and biophysics reports", "year": 2024, "abstract": "Gastric cancer is among the most prevalent cancers worldwide including in Pakistan. Late diagnosis of gastric cancer leads to reduced survival. The present study aimed to investigate biomarkers for early diagnosis and prognosis of gastric cancer. For this purpose, the ten microarray-based gene expression datasets (GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948) were retrieved from GEO database and analyzed by GEO2R to identify differentially expressed genes. Datasets were arranged in subsets of different dataset combinations to identify common DEGs. The gene ontology and functional pathway enrichment analysis of common DEGs was performed by DAVID tool. Pan-cancer analysis was conducted by UALCAN database. Survival analysis of common DEGs was done by Kaplan-Meier plotter. A total of 71 common DEGs were identified in different combinations of datasets. Among them, only 5 DEGs namely ATP4B, ATP4A, CCKBR, KCNJ15, and KCNJ16 were detected to be common in all the datasets. The GO and pathway analysis represented that the identified DEGs are involved in gastric acid secretion and collecting duct acid secretion pathways. Further expression validation of these five genes using three additional datasets (GSE31811, GSE26899, and GSE26272) confirmed their differential expression in gastric cancer samples. The pan-cancer analysis also revealed aberrant expression of DEGs in various cancers. The survival analysis showed the association of these 5 DEGs with poor survival of gastric cancer patients. To conclude, this study revealed a panel of 5 genes, which can be employed as diagnostic and prognostic biomarkers of gastric cancer patients.", "claims": [{"id": "claim-method", "statement": "Identification of DEGs was performed by GEO2R available at (http://www.ncbi.nlm.nih.gov/geo/geo2r).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39655267", "locator": "sections[4] \"Screening for differentially expressed genes (DEGs)\" paragraph 2", "quote": "Identification of DEGs was performed by GEO2R available at (http://www.ncbi.nlm.nih.gov/geo/geo2r)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39655267", "locator": "sections[22] \"Data availability\" paragraph 2", "quote": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified a five-gene panel—ATP4B, ATP4A, CCKBR, KCNJ15, and KCNJ16—as promising diagnostic and prognostic biomarkers for gastric cancer patients.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39655267", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "To conclude, this study revealed a panel of 5 genes, which can be employed as diagnostic and prognostic biomarkers of gastric cancer patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified a five-gene panel—ATP4B, ATP4A, CCKBR, KCNJ15, and KCNJ16—as promising diagnostic and prognostic biomarkers for gastric cancer patients.", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39655267"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE103236"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE103236"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39655267", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.bbrep.2024.101880", "sha256": "sha256:dae48929893aa2c5f73cae5bd151b89a78c77852a2c42704fc62063f13f770f5", "bytes": 41673, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.bbrep.2024.101880", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11626535", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE103236", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE103236", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE103236", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2758660", "GSM2758661", "GSM2758662", "GSM2758663", "GSM2758664", "GSM2758665", "GSM2758666", "GSM2758667", "GSM2758668", "GSM2758669", "GSM2758670", "GSM2758671", "GSM2758672", "GSM2758673", "GSM2758674", "GSM2758675", "GSM2758676", "GSM2758677", "GSM2758678"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Microarray gene expresion analysis for early and advanced gastric adenocarcinoma vs normal adjacent tissue.", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE112369", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112369", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE112369", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3309732", "GSM3309733", "GSM3309734", "GSM3309735", "GSM3309736", "GSM3309737", "GSM3309738", "GSM3309739", "GSM3309740", "GSM3309741", "GSM3309742", "GSM3309743", "GSM3309744", "GSM3309745", "GSM3309746", "GSM3309747", "GSM3309748", "GSM3309749", "GSM3309750", "GSM3309751", "GSM3309752", "GSM3309753", "GSM3309754", "GSM3309755", "GSM3309756", "GSM3309757", "GSM3309758", "GSM3309759", "GSM3309760", "GSM3309761", "GSM3309762", "GSM3309763", "GSM3309764", "GSM3309765", "GSM3309766", "GSM3309767", "GSM3309768", "GSM3309769", "GSM3309770", "GSM3309771", "GSM3309772", "GSM3309773", "GSM3309774", "GSM3309775", "GSM3309776", "GSM3309777", "GSM3309778", "GSM3309779", "GSM3309780", "GSM3309781", "GSM3309782", "GSM3309783", "GSM3309784", "GSM3309785", "GSM3309786", "GSM3309787", "GSM3309788", "GSM3309789", "GSM3309790", "GSM3309791", "GSM3309792", "GSM3309793"], "sample_count": 62, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Gene expression data of organoids derived from human gastric tumor and normal stomach samples.", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE118916", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE118916", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE118916", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3351220", "GSM3351221", "GSM3351222", "GSM3351223", "GSM3351224", "GSM3351225", "GSM3351226", "GSM3351227", "GSM3351228", "GSM3351229", "GSM3351230", "GSM3351231", "GSM3351232", "GSM3351233", "GSM3351234", "GSM3351235", "GSM3351236", "GSM3351237", "GSM3351238", "GSM3351239", "GSM3351240", "GSM3351241", "GSM3351242", "GSM3351243", "GSM3351244", "GSM3351245", "GSM3351246", "GSM3351247", "GSM3351248", "GSM3351249"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Expression data from human gastric tumor and human normal stomach tissues", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE13911", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE13911", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13911", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM350411", "GSM350412", "GSM350413", "GSM350414", "GSM350415", "GSM350416", "GSM350417", "GSM350418", "GSM350419", "GSM350420", "GSM350421", "GSM350422", "GSM350423", "GSM350424", "GSM350425", "GSM350426", "GSM350427", "GSM350428", "GSM350429", "GSM350430", "GSM350431", "GSM350432", "GSM350433", "GSM350434", "GSM350435", "GSM350436", "GSM350437", "GSM350438", "GSM350439", "GSM350440", "GSM350441", "GSM350442", "GSM350443", "GSM350444", "GSM350445", "GSM350446", "GSM350447", "GSM350448", "GSM350449", "GSM350450", "GSM350451", "GSM350452", "GSM350453", "GSM350454", "GSM350455", "GSM350456", "GSM350457", "GSM350458", "GSM350459", "GSM350460", "GSM350461", "GSM350462", "GSM350463", "GSM350464", "GSM350465", "GSM350466", "GSM350467", "GSM350468", "GSM350469", "GSM350470", "GSM350471", "GSM350472", "GSM350473", "GSM350474", "GSM350475", "GSM350476", "GSM350477", "GSM350478", "GSM350479"], "sample_count": 69, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from primary gastric tumors (MSI and MSS) and adjacent normal samples", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE161533", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE161533", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE161533", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4909553", "GSM4909554", "GSM4909555", "GSM4909556", "GSM4909557", "GSM4909558", "GSM4909559", "GSM4909560", "GSM4909561", "GSM4909562", "GSM4909563", "GSM4909564", "GSM4909565", "GSM4909566", "GSM4909567", "GSM4909568", "GSM4909569", "GSM4909570", "GSM4909571", "GSM4909572", "GSM4909573", "GSM4909574", "GSM4909575", "GSM4909576", "GSM4909577", "GSM4909578", "GSM4909579", "GSM4909580", "GSM4909581", "GSM4909582", "GSM4909583", "GSM4909584", "GSM4909585", "GSM4909586", "GSM4909587", "GSM4909588", "GSM4909589", "GSM4909590", "GSM4909591", "GSM4909592", "GSM4909593", "GSM4909594", "GSM4909595", "GSM4909596", "GSM4909597", "GSM4909598", "GSM4909599", "GSM4909600", "GSM4909601", "GSM4909602", "GSM4909603", "GSM4909604", "GSM4909605", "GSM4909606", "GSM4909607", "GSM4909608", "GSM4909609", "GSM4909610", "GSM4909611", "GSM4909612", "GSM4909613", "GSM4909614", "GSM4909615", "GSM4909616", "GSM4909617", "GSM4909618", "GSM4909619", "GSM4909620", "GSM4909621", "GSM4909622", "GSM4909623", "GSM4909624", "GSM4909625", "GSM4909626", "GSM4909627", "GSM4909628", "GSM4909629", "GSM4909630", "GSM4909631", "GSM4909632", "GSM4909633", "GSM4909634", "GSM4909635", "GSM4909636"], "sample_count": 84, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from esophageal squamous cell carcinoma patients", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE19826", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE19826", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19826", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM495051", "GSM495052", "GSM495053", "GSM495054", "GSM495055", "GSM495056", "GSM495057", "GSM495058", "GSM495059", "GSM495060", "GSM495061", "GSM495062", "GSM495063", "GSM495064", "GSM495065", "GSM495066", "GSM495067", "GSM495068", "GSM495069", "GSM495070", "GSM495071", "GSM495072", "GSM495073", "GSM495074", "GSM495075", "GSM495076", "GSM495077"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from gastric cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE26272", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE26272", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26272", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM645185", "GSM645186", "GSM645187", "GSM645188", "GSM645189", "GSM645190", "GSM645191", "GSM645192"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from control and ZNF145-overexpressing human mesenchymal stem cells (MSCs)", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE26899", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE26899", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26899", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM662374", "GSM662375", "GSM662376", "GSM662377", "GSM662378", "GSM662379", "GSM662380", "GSM662381", "GSM662382", "GSM662383", "GSM662384", "GSM662385", "GSM662386", "GSM662387", "GSM662388", "GSM662389", "GSM662390", "GSM662391", "GSM662392", "GSM662393", "GSM662394", "GSM662395", "GSM662396", "GSM662397", "GSM662398", "GSM662399", "GSM662400", "GSM662401", "GSM662402", "GSM662403", "GSM662404", "GSM662405", "GSM662406", "GSM662407", "GSM662408", "GSM662409", "GSM662410", "GSM662411", "GSM662412", "GSM662413", "GSM662414", "GSM662415", "GSM662416", "GSM662417", "GSM662418", "GSM662419", "GSM662420", "GSM662421", "GSM662422", "GSM662423", "GSM662424", "GSM662425", "GSM662426", "GSM662427", "GSM662428", "GSM662429", "GSM662430", "GSM662431", "GSM662432", "GSM662433", "GSM662434", "GSM662435", "GSM662436", "GSM662437", "GSM662438", "GSM662439", "GSM662440", "GSM662441", "GSM662442", "GSM662443", "GSM662444", "GSM662445", "GSM662446", "GSM662447", "GSM662448", "GSM662449", "GSM662450", "GSM662451", "GSM662452", "GSM662453", "GSM662454", "GSM662455", "GSM662456", "GSM662457", "GSM662458", "GSM662459", "GSM662460", "GSM662461", "GSM662462", "GSM662463", "GSM662464", "GSM662465", "GSM662466", "GSM662467", "GSM662468", "GSM662469", "GSM662470", "GSM662471", "GSM662472", "GSM662473", "GSM662474", "GSM662475", "GSM662476", "GSM662477", "GSM662478", "GSM662479", "GSM662480", "GSM662481"], "sample_count": 108, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Characterization of gene expression profiles of gastric cancer in the Korea University cohort", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE31811", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE31811", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31811", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM773455", "GSM774574", "GSM774575", "GSM774576", "GSM774577", "GSM774578", "GSM774579", "GSM774580", "GSM774581", "GSM774582", "GSM774583", "GSM774584", "GSM774922", "GSM774923", "GSM774924", "GSM774925", "GSM774926", "GSM774927", "GSM774928", "GSM774929", "GSM774930", "GSM774931", "GSM774932", "GSM774933", "GSM774934", "GSM774935", "GSM774936", "GSM774937", "GSM774938", "GSM774939", "GSM774947", "GSM774948", "GSM774949", "GSM774950", "GSM774951", "GSM774952", "GSM774953", "GSM774954"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "The genes associated with the response to S-1,cisplatin and docetaxel combination chemotherapy (DCS therapy) for metastatic gastric cancer:", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE33651", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33651", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33651", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM832257", "GSM832258", "GSM832259", "GSM832260", "GSM832261", "GSM832262", "GSM832263", "GSM832264", "GSM832265", "GSM832266", "GSM832267", "GSM832268", "GSM832269", "GSM832270", "GSM832271", "GSM832272", "GSM832273", "GSM832274", "GSM832275", "GSM832276", "GSM832277", "GSM832278", "GSM832279", "GSM832280", "GSM832281", "GSM832282", "GSM832283", "GSM832284", "GSM832285", "GSM832286", "GSM832287", "GSM832288", "GSM832289", "GSM832290", "GSM832291", "GSM832292", "GSM832293", "GSM832294", "GSM832295", "GSM832296", "GSM832297", "GSM832298", "GSM832299", "GSM832300", "GSM832301", "GSM832302", "GSM832303", "GSM832304", "GSM832305", "GSM832306", "GSM832307", "GSM832308"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "2895", "taxon": "Homo sapiens", "title": "Genome-wide gene expression profile of human gastric cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE54129", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE54129", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54129", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1308392", "GSM1308393", "GSM1308394", "GSM1308395", "GSM1308396", "GSM1308397", "GSM1308398", "GSM1308399", "GSM1308400", "GSM1308401", "GSM1308402", "GSM1308403", "GSM1308404", "GSM1308405", "GSM1308406", "GSM1308407", "GSM1308408", "GSM1308409", "GSM1308410", "GSM1308411", "GSM1308412", "GSM1308413", "GSM1308414", "GSM1308415", "GSM1308416", "GSM1308417", "GSM1308418", "GSM1308419", "GSM1308420", "GSM1308421", "GSM1308422", "GSM1308423", "GSM1308424", "GSM1308425", "GSM1308426", "GSM1308427", "GSM1308428", "GSM1308429", "GSM1308430", "GSM1308431", "GSM1308432", "GSM1308433", "GSM1308434", "GSM1308435", "GSM1308436", "GSM1308437", "GSM1308438", "GSM1308439", "GSM1308440", "GSM1308441", "GSM1308442", "GSM1308443", "GSM1308444", "GSM1308445", "GSM1308446", "GSM1308447", "GSM1308448", "GSM1308449", "GSM1308450", "GSM1308451", "GSM1308452", "GSM1308453", "GSM1308454", "GSM1308455", "GSM1308456", "GSM1308457", "GSM1308458", "GSM1308459", "GSM1308460", "GSM1308461", "GSM1308462", "GSM1308463", "GSM1308464", "GSM1308465", "GSM1308466", "GSM1308467", "GSM1308468", "GSM1308469", "GSM1308470", "GSM1308471", "GSM1308472", "GSM1308473", "GSM1308474", "GSM1308475", "GSM1308476", "GSM1308477", "GSM1308478", "GSM1308479", "GSM1308480", "GSM1308481", "GSM1308482", "GSM1308483", "GSM1308484", "GSM1308485", "GSM1308486", "GSM1308487", "GSM1308488", "GSM1308489", "GSM1308490", "GSM1308491", "GSM1308492", "GSM1308493", "GSM1308494", "GSM1308495", "GSM1308496", "GSM1308497", "GSM1308498", "GSM1308499", "GSM1308500", "GSM1308501", "GSM1308502", "GSM1308503", "GSM1308504", "GSM1308505", "GSM1308506", "GSM1308507", "GSM1308508", "GSM1308509", "GSM1308510", "GSM1308511", "GSM1308512", "GSM1308513", "GSM1308514", "GSM1308515", "GSM1308516", "GSM1308517", "GSM1308518", "GSM1308519", "GSM1308520", "GSM1308521", "GSM1308522", "GSM1308523"], "sample_count": 132, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Global gene expression analysis of gastric cancer by oligonucleotide microarrays", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE79973", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE79973", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE79973", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2109532", "GSM2109533", "GSM2109534", "GSM2109535", "GSM2109536", "GSM2109537", "GSM2109538", "GSM2109539", "GSM2109540", "GSM2109541", "GSM2109542", "GSM2109543", "GSM2109544", "GSM2109545", "GSM2109546", "GSM2109547", "GSM2109548", "GSM2109549", "GSM2109550", "GSM2109551"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from gastric cancer and paried normal tissues", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE81948", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE81948", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE81948", "version": null, "note": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2178316", "GSM2178317", "GSM2178318", "GSM2178319", "GSM2178320", "GSM2178321", "GSM2178322", "GSM2178323", "GSM2178324", "GSM2178325", "GSM2178326", "GSM2178327", "GSM2178328", "GSM2178329", "GSM2178330", "GSM2178331", "GSM2178332", "GSM2178333", "GSM2178334", "GSM2178335"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "miR-204 down-regulation elicited perturbation of a gene target signature common to human cholangiocarcinoma and gastric cancer.", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE103236 not downloaded", "asset:data:geo:GSE103236 licence not read", "asset:data:geo:GSE112369 not downloaded", "asset:data:geo:GSE112369 licence not read", "asset:data:geo:GSE118916 not downloaded", "asset:data:geo:GSE118916 licence not read", "asset:data:geo:GSE13911 not downloaded", "asset:data:geo:GSE13911 licence not read", "asset:data:geo:GSE161533 not downloaded", "asset:data:geo:GSE161533 licence not read", "asset:data:geo:GSE19826 not downloaded", "asset:data:geo:GSE19826 licence not read", "asset:data:geo:GSE26272 not downloaded", "asset:data:geo:GSE26272 licence not read", "asset:data:geo:GSE26899 not downloaded", "asset:data:geo:GSE26899 licence not read", "asset:data:geo:GSE31811 not downloaded", "asset:data:geo:GSE31811 licence not read", "asset:data:geo:GSE33651 not downloaded", "asset:data:geo:GSE33651 licence not read", "asset:data:geo:GSE54129 not downloaded", "asset:data:geo:GSE54129 licence not read", "asset:data:geo:GSE79973 not downloaded", "asset:data:geo:GSE79973 licence not read", "asset:data:geo:GSE81948 not downloaded", "asset:data:geo:GSE81948 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Identification of DEGs was performed by GEO2R available at (http://www.ncbi.nlm.nih.gov/geo/geo2r)."}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "logrank"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE54129", "GSE79973", "GSE161533", "GSE103236", "GSE33651", "GSE19826", "GSE118916", "GSE112369", "GSE13911", "GSE81948", "GSE31811", "GSE26899", "GSE26272"], "resolved_accessions": ["GSE54129", "GSE79973", "GSE161533", "GSE103236", "GSE33651", "GSE19826", "GSE118916", "GSE112369", "GSE13911", "GSE81948", "GSE31811", "GSE26899", "GSE26272"], "statements": ["The analyzed GEO datasets GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948 are available at (https://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, GSE81948, GSE31811, GSE26899, GSE26272 in Gene Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:39655267", "data:geo:GSE103236"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE103236"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:41:32Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11783, "completion_tokens": 4033, "cached_tokens": 128}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:39655267", "type": "paper", "label": "pmid:39655267"}, {"id": "source:pmid:39655267", "type": "manuscript", "label": "PMID 39655267 full text"}, {"id": "data:geo:GSE103236", "type": "dataset", "label": "GEO GSE103236"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39655267", "type": "paper", "label": "pmid:39655267"}, {"id": "source:pmid:39655267", "type": "manuscript", "label": "PMID 39655267 full text"}, {"id": "data:geo:GSE103236", "type": "dataset", "label": "GEO GSE103236"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39655267", "type": "extraction", "used": ["source:pmid:39655267"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE103236", "type": "accession_resolution", "used": ["data:geo:GSE103236"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:39655267", "parent_hash": "sha256:840b8040ff334be18056283ece363ee0c004494dd543b568cc02ebc139778687", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE103236 licence not read", "asset:data:geo:GSE103236 not downloaded", "asset:data:geo:GSE112369 licence not read", "asset:data:geo:GSE112369 not downloaded", "asset:data:geo:GSE118916 licence not read", "asset:data:geo:GSE118916 not downloaded", "asset:data:geo:GSE13911 licence not read", "asset:data:geo:GSE13911 not downloaded", "asset:data:geo:GSE161533 licence not read", "asset:data:geo:GSE161533 not downloaded", "asset:data:geo:GSE19826 licence not read", "asset:data:geo:GSE19826 not downloaded", "asset:data:geo:GSE26272 licence not read", "asset:data:geo:GSE26272 not downloaded", "asset:data:geo:GSE26899 licence not read", "asset:data:geo:GSE26899 not downloaded", "asset:data:geo:GSE31811 licence not read", "asset:data:geo:GSE31811 not downloaded", "asset:data:geo:GSE33651 licence not read", "asset:data:geo:GSE33651 not downloaded", "asset:data:geo:GSE54129 licence not read", "asset:data:geo:GSE54129 not downloaded", "asset:data:geo:GSE79973 licence not read", "asset:data:geo:GSE79973 not downloaded", "asset:data:geo:GSE81948 licence not read", "asset:data:geo:GSE81948 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["cer biomarkers through in-silico analysis of microarray based datasets.", "of gastric cancer. For this purpose, the ten microarray-based gene expression datasets (GSE54129, GS"], "order_basis": "paper_text_order:29", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Identification of DEGs was performed by GEO2R available at (http://www.ncbi.nlm.nih.gov/geo/geo2r)."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:07:30+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}